# Qwen3 235B A22B Instruct API prices

Qwen3 235B A22B Instruct (qwen) — 262k context, 64k max output.
2 metered per-token offers from 3 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DevPass (LLM Gateway) | $0.09 | $0.58 | — | 262k |
| Abacus | $0.13 | $0.6 | — | 262k |

## Summary

- Cheapest input: $0.09 per 1M tokens (DevPass (LLM Gateway))
- Cheapest output: $0.58 per 1M tokens (DevPass (LLM Gateway))
- First-party: not listed separately
- Free offers: iFlow
- Subscription plans (not per-token): none
- Released: 2025-07-01
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen3-235b-a22b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json